by OpenAI·Released 22 September 2026
GPT-6 Luna reads your text, pictures and files and writes back, and it can take in about a thousand pages at once. It is the quick, low-cost tier of the GPT-6 series, below GPT-6 Sol, built for heavy traffic and tight response times: chat, sorting messages into categories and light multi-step tasks. Turn its thinking up and it can also take software and computer-use jobs that used to need a Sol-class model.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 16,64 DA | 83,21 DA |
| Cached tokens read | 1,66 DA | |
| Cache-write tokens | 20,80 DA |
per 1M tokens
Web search · 3,33 DA per call, under every choice
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| OpenAI | 16,64 DA | 83,21 DA | 1,66 DA | … | … | … |
Also charged: prompts over 272 000 tokens ↑ 33,28 ↓ 124,81 · writing to the cache ↑ 20,80 · a web search 3,33 DA each.
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
Swap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="openai/gpt-6-luna:batch",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokensseedReasoning
Let it think before answering — and see the thinking.
reasoningreasoning_effortinclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceOther
Also accepted by this model.
verbosityAbout 0,058 DA per message. ↑ 16,64 DA · ↓ 83,21 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.
GPT-6 Luna reads your text, pictures and files and writes back, and it can take in about a thousand pages at once. It is the quick, low-cost tier of the GPT-6 series, below GPT-6 Sol, built for heavy traffic and tight response times: chat, sorting messages into categories and light multi-step tasks. Turn its thinking up and it can also take software and computer-use jobs that used to need a Sol-class model.
Deposit dinars with your Edahabia or CIB card. Every model, GPT-6 Luna (batch) included, is paid from that balance. No foreign card, no conversion.
OpenAI names no languages for GPT-6 Luna (batch). Arabic, French and Darja: not stated.
It reads text, images and PDFs. Up to 1.1M tokens in one request, about 1 000 pages. It writes up to 96 000 words at once.
No. OpenAI has not published its weights.
OpenAI. Released 22 September 2026. It knows the world up to May 2026.
Text Embedding 3 Small turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It replaces the older ada-002 and is the sensible default for search over your documents, grouping similar messages or labelling them.
GPT Image 2.5 Sunburst takes a written description, with optional reference pictures, and gives back an image, new or edited, as PNG, JPEG or WebP, with transparent backgrounds on PNG and WebP. It is the precision tier of the 2.5 series, for detailed creative work where an edit has to land exactly as asked, and it adds top quality settings named xhigh and max.
GPT-6 Luna Decisions does not write text. You send content as text, a table of data or a picture, plus up to 200 named questions of three kinds: yes or no, pick among options, or grade against an ordered scale. It returns a probability for every answer, with the likeliest option or expected score, so your own system can set its thresholds for routing, moderation or marking.
Text Embedding 3 Large turns text of up to about 8 pages into a fingerprint of its meaning, so search finds passages that mean the same thing even when the words differ. It is the most accurate of OpenAI's models of this kind, in English and other languages. Choose it when the quality of matches matters most, for search, grouping or labelling documents.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights No.
Read on developers.openai.com.
Knows events up to May 2026
Read on developers.openai.com.
Sort thousands of support tickets by topic and urgency
Fills your JSON
Answer customer chat messages and look up their orders through your tools
Uses your tools
Pull the fields out of a scanned delivery note into JSON
Images · Fills your JSON